Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    own

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prominence
    -0.06
     graduating
    -0.06
    urch
    -0.06
    Sir
    -0.06
     telah
    -0.06
    Platforms
    -0.06
    .i
    -0.06
     subscriptions
    -0.06
    Honda
    -0.06
     }(
    -0.06
    POSITIVE LOGITS
     Рос
    0.07
    ونا
    0.07
    Adult
    0.07
     ром
    0.06
     przed
    0.06
    216
    0.06
    Classic
    0.06
    _Integer
    0.06
     stance
    0.06
    итор
    0.06
    Act Density 0.083%

    No Known Activations